Traffic Sign Instances Segmentation Using Aliased Residual Structure and Adaptive Focus Localizer

Shi, Wenjun; Shi, Yonghong; Zhu, Dongchen; Zhang, Xiaolin; Li, Jiamao

doi:10.1109/icpr56361.2022.9956293

Cited by 1 publication

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is usually used as the Neck part of the model to fuse feature maps from different layers in the Backbone to obtain rich semantic and localization information. The Path Aggregation Network (PANet) [24] is a widely used feature fusion network in general-purpose object detection algorithms, which utilizes both top-down and bottom-up aggregation paths to fully fuse shallow high-resolution features and deep low-resolution features for more accurate object detection [25]. However, existing PANet feature fusion networks do not consider the model lightweight, and the computational and parameter costs need to be reduced and optimized.…”

Section: Lightweight Neck Networkmentioning

confidence: 99%

SP-YOLO-Lite: A Lightweight Violation Detection Algorithm Based on SP Attention Mechanism

Huang

Xie

et al. 2023

Electronics

View full text Add to dashboard Cite

In the operation site of power grid construction, it is crucial to comprehensively and efficiently detect violations of regulations for the personal safety of the workers with a safety monitoring system based on object detection technology. However, common general-purpose object detection algorithms are difficult to deploy on low-computational-power embedded platforms situated at the edge due to their high model complexity. These algorithms suffer from drawbacks such as low operational efficiency, slow detection speed, and high energy consumption. To address this issue, a lightweight violation detection algorithm based on the SP (Segmentation-and-Product) attention mechanism, named SP-YOLO-Lite, is proposed to improve the YOLOv5s detection algorithm and achieve low-cost deployment and efficient operation of object detection algorithms on low-computational-power monitoring platforms. First, to address the issue of excessive complexity in backbone networks built with conventional convolutional modules, a Lightweight Convolutional Block was employed to construct the backbone network, significantly reducing computational and parameter costs while maintaining high detection model accuracy. Second, in response to the problem of existing attention mechanisms overlooking spatial local information, we introduced an image segmentation operation and proposed a novel attention mechanism called Segmentation-and-Product (SP) attention. It enables the model to effectively capture local informative features of the image, thereby enhancing model accuracy. Furthermore, a Neck network that is both lightweight and feature-rich is proposed by introducing Depthwise Separable Convolution and Segmentation-and-Product attention module to Path Aggregation Network, thus addressing the issue of high computation and parameter volume in the Neck network of YOLOv5s. Experimental results show that compared with the baseline network YOLOv5s, the proposed SP-YOLO-Lite model reduces the computation and parameter volume by approximately 70%, achieving similar detection accuracy on both the VOC dataset and our self-built SMPC dataset.

show abstract

Section: Lightweight Neck Networkmentioning

confidence: 99%